Type | |
Stats | 715 |
Reviews | (75) |
Published | Dec 11, 2023 |
Base Model | |
Trigger Words | (tutututu), (red edge thighhighs), (red edge stockings), |
Hash | AutoV2 01252B377D |
交流Q群：950351015，欢迎来玩，互通有无。
电报：https://t.me/+nbU3j7rLEYZkNzVl。
V2.0
The previous version was not easy to use. I don't even think it's useful enough.
So I made new ones.
Easier to trigger red edge effect.
The prompt words are: (tutututu), (red edge thighhighs), (rededgestockings),
It is recommended to try from (tutututu:1.3), (red edge thighhighs), (rededgestockings).
It's much better than the previous one. If it doesn't come out, consider it is the influence of the tag and the bottom film. Try changing it.
The pollution is very small, almost non-existent, and the impact will not be significant if the weight is set to 0.9.
Carefully crafted using differential extraction method.
之前的版本不好用。我自己都觉得不够好用。
所以我做了新的。
更容易触发红边效果。
提示词是：(tutututu), (red edge thighhighs), (rededgestockings),
建议从(tutututu:1.3), (red edge thighhighs), (rededgestockings),开始尝试。
相比之前的好太多了，如果没出来的话考虑是tag和底膜的影响，换一换试试。
污染很小，几乎没有，权重开到0.9影响也不大。
采用差异提取法精心制作。
V1.0
简介：
这是一个8D红边黑色长筒袜，可以改善图中丝袜的质感。
厚度：8D
颜色：black
类型：8D红边黑色过膝袜
本LORA的特点如下：
1、使用差异提取法精心制作，除了会对**的质感产生影响以外，对画面的其他内容影响较小。
2、全部采用真人照片高清相机拍摄制作，确保效果真实。
为什么已经有了这么多黑丝LORA，还要再做一个？因为我发现：
1、现有的LORA都会对画面产生一些污染。要不然是衣服，要不然是鞋，要不然是身材。可否做一个LORA，只会对黑丝的质感产生影响，而不会对其他画面内容产生影响？
2、现有的LORA都没有对**的厚度、样式等进行细分，整体是一个比较混乱的状态。
所以我制作了这个LORA，后期还会制作一系列不同的厚度、质感的LORA，均采用真实实拍素材，使用差异提取法进行制作，确保质量。
所以这有可能是你用过的最好的嗨丝LORA。
使用方法：
1、确保你正确的使用LORA.
2、CLIP 终止层数建议设置为2.
3、如果对其他服装以及环境没有任何描述，**的LORA可能会对环境有一些影响。但是如果加了描述词后，影响就会降低甚至没有影响。
4、触发词为：red thighhighs,tutuhb,起手可以设置为：
(red thighhighs),(tutuhb:1.5), <lora:tutuhb_v6:0.7>
5、负面不要加的太多，否则会对LORA的效果产生影响。
6、提示词引导系数 (CFG Scale)可以从7开始尝试。
7、LoRA Block Weight (LoRA 区块权重配置)我没有打开。也可以打开试试？我没试过。
8、目前尝试的大模型比较好的有，大颗寿司系列，墨幽系列，ghostshell系列，也就是2次元，2.5，真人都适用。对于不同的大模型，需要对参数进行调试。
如果您在使用中遇到问题，可以给我留言。
期待您的作品！
期待您的作品！
期待您的作品！
声明：
1、您应对使用此模型的任何创意作品承担全部责任。
2、您不能使用该模型故意制作或分享非法或有害的输出或内容，避免将此模型用于恶意、伤害、诽谤、诈骗或政治用途。
3、如果将本模型用于商业用途，请通知我，谢谢。
常见问题：
1、为什么我出不了和你一样的照片？
每个人的电脑配置以及操作环境都不一样，使用的LORA以及插件版本、插件配置等也会有所区别，所以请不要追求一模一样的照片，创作您自己的完美作品吧！
2、权重调高以后图片出现大面积马赛克怎么办？
尝试调低权重，或者降低其他LORA的权重，或者打开LoRA Block Weight插件。
3、如何取得联系？
如果有定制LORA的需求，或者有其他合作意向，可以直接在这里留言，或者联系Q331506796（注明来意）
Introduction:
This is a black stocking with 8D red edge, which can improve the texture of stockings in the picture.
Thickness: 8D
color: black
Type: 8D red edge black knee socks
The characteristics of this LORA are as follows:
1. Elaborately produced using the difference extraction method, except for the impact on the texture of the image, it has little impact on other content of the picture.
2. All photos are taken with real-life high-definition cameras to ensure real effects.
Why do you want to make another one after there are already so many black silk LORAs? because I found:
1. The existing LORA will cause some pollution to the picture. Either clothes, or shoes, or body. Is it possible to make a LORA, which will only affect the texture of the black silk, but not other screen content?
2. The existing LORA does not subdivide the thickness and style of the hair, and the overall situation is rather chaotic.
So I made this LORA, and later I will make a series of LORAs with different thicknesses and textures, all of which are made of real-life materials and made using the difference extraction method to ensure the quality.
So this might be the best HISI LORA you've ever used.
Instructions:
1. Make sure you use LORA correctly.
2. It is recommended to set the number of CLIP termination layers to 2.
3. If there is no description of other clothing and the environment, **LORA may have some impact on the environment. But if descriptors are added, the impact will be reduced or even have no impact.
4. The trigger word is: red thighhighs, tutuhb, the starting hand can be set as:
(red thighhighs),(tutuhb:1.5), <lora:tutuhb_v6:0.7>
5. Don't add too much negative, otherwise it will affect the effect of LORA.
6. You can start from 7 for the prompt word guide coefficient (CFG Scale).
7. LoRA Block Weight (LoRA block weight configuration) I have not opened. Can you also open it? I haven't tried it.
8. The large models currently tried are relatively good, such as the large sushi series, the Moyou series, and the ghostshell series, which are 2-dimensional, 2.5, and are suitable for real people. For different large models, parameters need to be adjusted.
If you encounter problems in use, you can leave me a message.
Looking forward to your work!
Looking forward to your work!
Looking forward to your work!
statement:
1. You are solely responsible for any creative work using this mockup.
2. You cannot use this model to intentionally produce or share illegal or harmful output or content, and avoid using this model for malicious, hurtful, defamatory, fraudulent or political purposes.
3. If you use this model for commercial purposes, please notify me, thank you.
common problem:
1. Why can't I post the same photos as you?
Everyone's computer configuration and operating environment are different, and the LORA used, plug-in version, plug-in configuration, etc. will also be different, so please don't pursue exactly the same photos, create your own perfect work!
2. What should I do if there is a large area of mosaic in the picture after the weight is increased?
Try to lower the weight, or lower the weight of other LORA, or turn on the LoRA Block Weight plugin.
3. How to get in touch?
If you have a need to customize LORA, or have other cooperation intentions, you can leave a message here directly, or contact Q331506796 (indicate your intention)